The social media MCP server. Twenty tools over one endpoint.
A Streamable HTTP MCP server that reads your brands and channels, prices and generates video and text, takes your own uploads, schedules and sends posts, and reads back how they did.
An AI agent asks for two videos about a serum, gets the price first, generates them, writes the posts and schedules them for Thursday at 11:30 on every connected channel.
MCP server
- Tools
- 20
- Scopes
- 3
- Channels
- 7
- Endpoint
- 1
Point your client at the endpoint
Mint a personal access token first. The secret is shown once, and it works on this endpoint only.
POST https://www.socialfaktory.com/mcp
Any Streamable HTTP client
POST https://www.socialfaktory.com/mcpAuthorization: Bearer sfp_…Content-Type: application/jsonAccept: application/json, text/event-streamMCP-Protocol-Version: 2025-06-18{ "jsonrpc": "2.0", "id": 1, "method": "tools/list" }
Claude Code
claude mcp add -s user --transport http socialfaktory https://www.socialfaktory.com/mcp \--header "Authorization: Bearer sfp_…"
Codex CLI
export SOCIALFAKTORY_TOKEN=sfp_…codex mcp add socialfaktory --url https://www.socialfaktory.com/mcp --bearer-token-env-var SOCIALFAKTORY_TOKEN
OpenClaw CLI
openclaw mcp set socialfaktory '{"url":"https://www.socialfaktory.com/mcp","transport":"streamable-http","headers":{"Authorization":"Bearer sfp_…"}}'
What the agent can do
20 tools, grouped by what they touch. Every tool names the scope it needs, and a token without that scope is refused before the tool runs.
Reading what you have
list_brandsReadFreelist_channelsReadFreeget_channel_requirementsReadFreelist_formatsReadFreeget_walletReadFree
Making something new
quote_generationReadFreecreate_generationGenerateSpends creditsgenerate_textGenerateSpends creditscheck_referenceReadFree
Reading results
get_generationReadFreelist_generationsReadFreeget_text_generationReadFreelist_mediaReadFree
Bringing your own file
create_uploadGenerateFreecomplete_uploadGenerateFreeget_uploadReadFree
Publishing
create_postsPublishFreesend_postPublishFreedelete_postPublishFreelist_postsReadFree
How permissions work
- Every token can read. Add generate for anything that spends credits, and publish for creating, scheduling, sending and deleting posts.
- Pin a token to one brand and it sees only that brand, with its channels, generations, posts and text. The credit wallet, uploads, actors and products stay shared across the account.
- Set a monthly credit cap and the token starts no paid call once the month's spend reaches it.
- Every call that spends or publishes carries an idempotency key. A replay inside 24 hours returns the first result instead of doing the work twice.
- 120 calls a minute per token, and 300 requests every 5 minutes per address.
What it will not do
- Clone a video from a link. That one runs in the app only.
- Generate still images or carousels. Neither is available through an agent yet.
- Connect a social channel. Connecting one is a browser sign-in, so it stays in the app.
- Start a paid call that would pass the cap you set on the token, or change your plan.
A typical run
- Step 1
Mint the token
Pick its scopes, pin it to a brand, set a monthly cap. The secret is shown once.
- Step 2
Ask for a price
quote_generation prices a video for free. It is an optional check, and a render runs without one.
- Step 3
Generate
create_generation makes the video and charges its price. generate_text reserves a few credits and settles what the write used. Both hand back an id you read the result from.
- Step 4
Schedule it
create_posts composes one post per channel, and send_post puts it on its channel now or at its time.
Questions
What transport does the server use?
Streamable HTTP on POST /mcp, protocol version 2025-06-18. A GET answers 405.
Is there a session to keep alive?
No. The bearer token is the session, so every call carries the Authorization header and nothing else.
Which tools does the server expose?
Five groups, reading what you have, making something new, reading results, bringing your own file, and publishing. Every tool names the scope it needs.
Is it safe to retry a call?
Yes. Everything that spends or publishes takes an idempotency key, and a replay inside 24 hours returns the first result marked as a replay.
What are the rate limits?
120 calls a minute per token, and 300 requests every 5 minutes per address.
Does it support OAuth?
Yes. Claude Desktop, claude.ai, ChatGPT and Gemini add the endpoint as a custom connector and sign in through a consent screen, with no token to paste. Clients that take a bearer token still work with one you mint yourself.
Let an agent run the brand.
Mint a token, point your client at the endpoint, and brief it the way you would brief a person.
Rated 4.9/5 by 180+ content teams · First video in about 7 minutes · Nothing goes live until you schedule it
Every token can read. Add generate for anything that spends credits, and publish for creating, scheduling, sending and deleting posts.
Pin a token to one brand and it sees only that brand, with its channels, generations, posts and text. The credit wallet, uploads, actors and products stay shared across the account.
Set a monthly credit cap and the token starts no paid call once the month's spend reaches it.
Every call that spends or publishes carries an idempotency key. A replay inside 24 hours returns the first result instead of doing the work twice.
120 calls a minute per token, and 300 requests every 5 minutes per address.


